Editing Geographic information system (section)

==Spatial analysis{{anchor|Spatial analysis}}==
{{further|Spatial analysis}}

GIS spatial analysis is a rapidly changing field, and GIS packages are increasingly including analytical tools as standard built-in facilities, as optional toolsets, as add-ins or 'analysts'. In many instances these are provided by the original software suppliers (commercial vendors or collaborative non commercial development teams), while in other cases facilities have been developed and are provided by third parties. Furthermore, many products offer software development kits (SDKs), programming languages and language support, scripting facilities and/or special interfaces for developing one's own analytical tools or variants. The increased availability has created a new dimension to [[business intelligence]] termed "[[Spatial intelligence (business method)|spatial intelligence]]" which, when openly delivered via intranet, democratizes access to geographic and social network data. [[Geospatial intelligence]], based on GIS spatial analysis, has also become a key element for security. GIS as a whole can be described as conversion to a vectorial representation or to any other digitisation process.

{{anchor|Geoprocessing}}'''Geoprocessing'''<!--boldface per [[WP:R#PLA]]--> is a GIS operation used to manipulate spatial data. A typical geoprocessing operation takes an input [[dataset]], performs an operation on that dataset, and returns the result of the operation as an output dataset. Common geoprocessing operations include geographic feature overlay, feature selection and analysis, [[topology]] processing, [[raster graphics|raster]] processing, and data conversion. Geoprocessing allows for definition, management, and analysis of information used to form decisions.<ref>Wade, T. and Sommer, S. eds. ''[http://store.esri.com/esri/showdetl.cfm?SID=2&Product_ID=868&Category_ID=49 A to Z GIS]''</ref>

===Terrain analysis===
[[File:Dem.jpg|thumb|right|300px|Hillshade model derived from a [[digital elevation model]] of the Valestra area in the northern Apennines (Italy)]]
{{main|Geomorphometry}}
{{see also|Surface gradient}}
Many geographic tasks involve the [[terrain]], the shape of the surface of the earth, such as [[hydrology]], [[Earthworks (engineering)|earthworks]], and [[biogeography]]. Thus, terrain data is often a core dataset in a GIS, usually in the form of a raster [[Digital elevation model]] (DEM) or a [[Triangulated irregular network]] (TIN). A variety of tools are available in most GIS software for analyzing terrain, often by creating derivative datasets that represent a specific aspect of the surface. Some of the most common include:
* [[Grade (slope)|Slope or grade]] is the steepness or gradient of a unit of terrain, usually measured as an angle in degrees or as a percentage.<ref name=Jones1998>{{cite journal |doi= 10.1016/S0098-3004(98)00032-6 |author = Jones, K.H.|year=1998 |title=A comparison of algorithms used to compute hill slope as a property of the DEM |journal=Computers and Geosciences |volume=24 |issue=4 |pages =315–323 |bibcode=1998CG.....24..315J}}</ref> 
* [[Aspect (geography)|Aspect]] can be defined as the direction in which a unit of terrain faces. Aspect is usually expressed in degrees from north.<ref name="Skidmore1989">{{cite journal |author1 =Chang, K. T.|year=1989|title=A comparison of techniques for calculating gradient and aspect from a gridded digital elevation model|journal=International Journal of Geographical Information Science|volume=3|issue=4|pages =323–334 |doi=10.1080/02693798908941519|url=https://research.utwente.nl/en/publications/470392f6-30d7-45df-806b-a29aa84aaa72 }}</ref> 
* Cut and fill is a computation of the difference between the surface before and after an [[Earthworks (engineering)|excavation]] project to estimate costs.
* [[Hydrological model]]ing can provide a spatial element that other hydrological models lack, with the analysis of variables such as slope, aspect and watershed or [[Catchment area (human geography)|catchment area]].<ref name="Heywood">{{cite book |vauthors=Heywood I, Cornelius S, Carver S |year=2006 |title=An Introduction to Geographical Information Systems |publisher=Prentice Hall |place=Essex, England |edition = 3rd}}</ref> Terrain analysis is fundamental to hydrology, since water always flows down a slope.<ref name="Heywood" /> As basic terrain analysis of a [[digital elevation model]] (DEM) involves calculation of slope and aspect, DEMs are very useful for hydrological analysis. Slope and aspect can then be used to determine direction of [[surface runoff]], and hence flow accumulation for the formation of streams, rivers and lakes. Areas of divergent flow can also give a clear indication of the boundaries of a catchment. Once a flow direction and accumulation matrix has been created, queries can be performed that show contributing or dispersal areas at a certain point.<ref name="Heywood" /> More detail can be added to the model, such as terrain roughness, vegetation types and soil types, which can influence infiltration and evapotranspiration rates, and hence influencing surface flow. One of the main uses of hydrological modeling is in [[GIS in environmental contamination|environmental contamination research]]. Other applications of hydrological modeling include [[GIS and hydrology|groundwater and surface water mapping]], as well as flood risk maps.
* [[Viewshed analysis]] predicts the impact that terrain has on the visibility between locations, which is especially important for wireless communications.
* [[Shaded relief]] is a depiction of the surface as if it were a three dimensional model lit from a given direction, which is very commonly used in maps.

Most of these are generated using algorithms that are discrete simplifications of [[vector calculus]]. Slope, aspect, and surface curvature in terrain analysis are all derived from neighborhood operations using elevation values of a cell's adjacent neighbours.<ref name="Chang">{{cite book |author=Chang, K. T. |year=2008 |title=Introduction to Geographical Information Systems |publisher=McGraw Hill |place=New York |page =184}}</ref> Each of these is strongly affected by the level of detail in the terrain data, such as the resolution of a DEM, which should be chosen carefully.<ref name="Longley2005">{{cite journal |author1 =Longley, P. A. |author2 =Goodchild, M. F. |author3 =McGuire, D. J. |author4 = Rhind, D. W. |year=2005 |title=Analysis of errors of derived slope and aspect related to DEM data properties |journal=Geographic Information Systems and Science |publisher=John Wiley and Sons |place=West Sussex, England |page=328}}</ref>

===Proximity analysis===
{{main|Proximity analysis}}
Distance is a key part of solving many geographic tasks, usually due to the [[friction of distance]]. Thus, a wide variety of analysis tools have analyze distance in some form, such as [[Buffer analysis|buffers]], [[Voronoi diagram|Voronoi or Thiessen polygons]], [[Cost distance analysis]], and [[Transport network analysis|network analysis]].

===Data analysis===
It is difficult to relate [[wetlands]] maps to [[rainfall]] amounts recorded at different points such as airports, television stations, and schools. A GIS, however, can be used to depict two- and three-dimensional characteristics of the Earth's surface, subsurface, and atmosphere from information points. For example, a GIS can quickly generate a map with [[isopleth]] or [[contour line]]s that indicate differing amounts of rainfall. Such a map can be thought of as a rainfall contour map. Many sophisticated methods can estimate the characteristics of surfaces from a limited number of point measurements. A two-dimensional contour map created from the surface modeling of rainfall point measurements may be overlaid and analyzed with any other map in a GIS covering the same area. This GIS derived map can then provide additional information - such as the viability of [[water power]] potential as a [[renewable energy]] source. Similarly, GIS can be used to compare other [[renewable energy]] resources to find the best geographic potential for a region.<ref>K. Calvert, J. M. Pearce, W.E. Mabee, "Toward renewable energy geo-information infrastructures: Applications of GIScience and remote sensing that can build institutional capacity" ''Renewable and Sustainable Energy Reviews'' 18, pp. 416–429 (2013). [https://www.academia.edu/2180165/Toward_renewable_energy_geo-information_infrastructures_Applications_of_GIScience_and_remote_sensing_that_build_institutional_capacity open access]</ref>

Additionally, from a series of three-dimensional points, or [[digital elevation model]], isopleth lines representing elevation contours can be generated, along with slope analysis, [[shaded relief]], and other elevation products. Watersheds can be easily defined for any given reach, by computing all of the areas contiguous and uphill from any given point of interest. Similarly, an expected [[thalweg]] of where surface water would want to travel in intermittent and permanent streams can be computed from elevation data in the GIS.

===Topological modeling===
A GIS can recognize and analyze the spatial relationships that exist within digitally stored spatial data. These [[topological]] relationships allow complex spatial modelling and analysis to be performed. Topological relationships between geometric entities traditionally include adjacency (what adjoins what), containment (what encloses what), and proximity (how close something is to something else).

===Geometric networks===
{{main | Transport network analysis }}

[[Geometric networks]] are linear networks of objects that can be used to represent interconnected features, and to perform special spatial analysis on them. A geometric network is composed of edges, which are connected at junction points, similar to [[Graph (discrete mathematics)|graphs]] in mathematics and computer science. Just like graphs, networks can have weight and flow assigned to its edges, which can be used to represent various interconnected features more accurately. Geometric networks are often used to model road networks and [[public utility]] networks, such as electric, gas, and water networks. Network modeling is also commonly employed in [[transportation planning]], [[hydrology]] modeling, and [[infrastructure]] modeling.

===Cartographic modeling===
{{main | Map algebra}}
[[File:gislayers.jpg|300px|right|thumb| An example of use of layers in a GIS application. In this example, the forest-cover layer (light green) forms the bottom layer, with the [[topography|topographic]] layer (contour lines) over it. Next up is a standing water layer (pond, lake) and then a flowing water layer (stream, river), followed by the boundary layer and finally the road layer on top. The order is very important in order to properly display the final result. Note that the ponds are layered under the streams, so that a stream line can be seen overlying one of the ponds.]]

[[Dana Tomlin]] coined the term ''cartographic modeling'' in his PhD dissertation (1983); he later used it in the title of his book, ''Geographic Information Systems and Cartographic Modeling'' (1990).<ref>{{cite book | last1 = Tomlin | first1 = C. Dana | author-link1 = Dana Tomlin | title = Geographic information systems and cartographic modeling | url = https://archive.org/details/geographicinform00toml | url-access = registration | series = Prentice Hall series in geographic information science | publisher = Prentice Hall | date = 1990 | isbn = 9780133509274 | access-date = 5 January 2017}}</ref> [[cartographic design|Cartographic modeling]] refers to a process where several thematic [[layer (disambiguation)|layers]] of the same area are produced, processed, and analyzed. Tomlin used raster layers, but the overlay method (see below) can be used more generally. Operations on map layers can be combined into algorithms, and eventually into simulation or optimization models.

===Map overlay===
{{main | Vector overlay | Map algebra }}
The combination of several spatial datasets (points, lines, or [[polygons]]) creates a new output vector dataset, visually similar to stacking several maps of the same region. These overlays are similar to mathematical [[Venn diagram]] overlays. A [[union (set theory)|union]] overlay combines the geographic features and attribute tables of both inputs into a single new output. An [[intersection (set theory)|intersect]] overlay defines the area where both inputs overlap and retains a set of attribute fields for each. A [[symmetric difference]] overlay defines an output area that includes the total area of both inputs except for the overlapping area.

Data extraction is a GIS process similar to vector overlay, though it can be used in either vector or raster data analysis. Rather than combining the properties and features of both datasets, data extraction involves using a "clip" or "mask" to extract the features of one data set that fall within the spatial extent of another dataset.

In raster data analysis, the overlay of datasets is accomplished through a process known as "local operation on multiple rasters" or "[[map algebra]]", through a function that combines the values of each raster's [[matrix (mathematics)|matrix]]. This function may weigh some inputs more than others through use of an "index model" that reflects the influence of various factors upon a geographic phenomenon.

===Geostatistics===
{{Main|Geostatistics}}

[[Geostatistics]] is a branch of statistics that deals with field data, spatial data with a continuous index. It provides methods to model spatial correlation, and predict values at arbitrary locations (interpolation).

When phenomena are measured, the observation methods dictate the accuracy of any subsequent analysis. Due to the nature of the data (e.g. traffic patterns in an urban environment; weather patterns over the [[Pacific Ocean]]), a constant or dynamic degree of precision is always lost in the measurement. This loss of precision is determined from the scale and distribution of the data collection.

To determine the statistical relevance of the analysis, an average is determined so that points (gradients) outside of any immediate measurement can be included to determine their predicted behavior. This is due to the limitations of the applied statistic and data collection methods, and interpolation is required to predict the behavior of particles, points, and locations that are not directly measurable.

[[Interpolation]] is the process by which a surface is created, usually a raster dataset, through the input of data collected at a number of sample points. There are several forms of interpolation, each which treats the data differently, depending on the properties of the data set. In comparing interpolation methods, the first consideration should be whether or not the source data will change (exact or approximate). Next is whether the method is subjective, a human interpretation, or objective. Then there is the nature of transitions between points: are they abrupt or gradual. Finally, there is whether a method is global (it uses the entire data set to form the model), or local where an algorithm is repeated for a small section of terrain.

Interpolation is a justified measurement because of a spatial autocorrelation principle that recognizes that data collected at any position will have a great similarity to, or influence of those locations within its immediate vicinity.

[[Digital elevation model]]s, [[triangulated irregular network]]s, edge-finding algorithms, [[Thiessen polygons]], [[Fourier analysis]], [[Weighted moving average|(weighted) moving averages]], [[inverse distance weighting]], [[kriging]], [[Spline (mathematics)|spline]], and [[Trend estimation|trend surface analysis]] are all mathematical methods to produce interpolative data.

===Address geocoding===
{{Main|Geocoding}}
Geocoding is interpolating spatial locations (X,Y coordinates) from street addresses or any other spatially referenced data such as [[ZIP&nbsp;Code]]s, [[Land lot|parcel lots]] and address locations. A reference theme is required to [[Geocoding|geocode]] individual addresses, such as a road centerline file with address ranges. The individual address locations have historically been interpolated, or estimated, by examining address ranges along a road segment. These are usually provided in the form of a table or database. The software will then place a dot approximately where that address belongs along the segment of centerline. For example, an address point of 500 will be at the midpoint of a line segment that starts with address&nbsp;1 and ends with address&nbsp;1,000. Geocoding can also be applied against actual parcel data, typically from municipal tax maps. In this case, the result of the geocoding will be an actually positioned space as opposed to an interpolated point. This approach is being increasingly used to provide more precise location information.

===Reverse geocoding===
{{main|Reverse geocoding}}
Reverse geocoding is the process of returning an estimated [[street address]] number as it relates to a given coordinate. For example, a user can click on a road centerline theme (thus providing a coordinate) and have information returned that reflects the estimated house number. This house number is interpolated from a range assigned to that road segment. If the user clicks at the [[midpoint]] of a segment that starts with address&nbsp;1 and ends with&nbsp;100, the returned value will be somewhere near 50. Note that reverse geocoding does not return actual addresses, only estimates of what should be there based on the predetermined range.

===Multi-criteria decision analysis===
{{main | Multiple-criteria decision analysis}}
Coupled with GIS, [[multi-criteria decision analysis]] methods support decision-makers in analysing a set of alternative spatial solutions, such as the most likely ecological habitat for restoration, against multiple criteria, such as vegetation cover or roads. MCDA uses decision rules to aggregate the criteria, which allows the alternative solutions to be ranked or prioritised.<ref name="Greene">{{cite journal | last1 = Greene | first1 = R. | last2 = Devillers | first2 = R. | last3 = Luther | first3 = J.E. | last4 = Eddy | first4 = B.G. | title = GIS-based multi-criteria analysis | journal = Geography Compass | year = 2011 | volume = 5/6 | issue = 6 | pages = 412–432 | doi = 10.1111/j.1749-8198.2011.00431.x }}</ref> GIS MCDA may reduce costs and time involved in identifying potential restoration sites.

===GIS data mining===
GIS or spatial [[data mining]] is the application of data mining methods to spatial data. Data mining, which is the partially automated search for hidden patterns in large databases, offers great potential benefits for applied GIS-based&nbsp;decision&nbsp;making. Typical applications include [[environmental monitoring]]. A characteristic of such applications is that spatial correlation between data measurements require the use of specialized algorithms for more efficient data analysis.<ref>{{Cite journal | last1 = Ma | first1 = Y. | last2 = Guo | first2 = Y. | last3 = Tian | first3 = X. | last4 = Ghanem | first4 = M. | title = Distributed Clustering-Based Aggregation Algorithm for Spatial Correlated Sensor Networks | doi = 10.1109/JSEN.2010.2056916 | journal = IEEE Sensors Journal | volume = 11 | issue = 3 | page = 641 | year = 2011 | url = http://www.inf.ufpr.br/carmem/oficinaBD/artigos1s2014/dist-clustering.pdf | bibcode = 2011ISenJ..11..641M | citeseerx = 10.1.1.724.1158 | s2cid = 1639100 }}</ref>